TYP: enable reportUnknownVariableType

pandas-stubs/__init__.pyi

@@ -47,7 +47,6 @@ from pandas.core.api import (
     UInt16Dtype as UInt16Dtype,
     UInt32Dtype as UInt32Dtype,
     UInt64Dtype as UInt64Dtype,
-    array as array,
     bdate_range as bdate_range,
     date_range as date_range,
     factorize as factorize,
@@ -66,6 +65,7 @@ from pandas.core.api import (
 )
 from pandas.core.arrays.sparse import SparseDtype as SparseDtype
 from pandas.core.computation.api import eval as eval
+from pandas.core.construction import array as array
 from pandas.core.reshape.api import (
     concat as concat,
     crosstab as crosstab,
@@ -100,13 +100,11 @@ from pandas.io.api import (
     HDFStore as HDFStore,
     read_clipboard as read_clipboard,
     read_csv as read_csv,
-    read_excel as read_excel,
     read_feather as read_feather,
     read_fwf as read_fwf,
     read_hdf as read_hdf,
     read_html as read_html,
     read_json as read_json,
-    read_orc as read_orc,
     read_parquet as read_parquet,
     read_pickle as read_pickle,
     read_sas as read_sas,
@@ -118,6 +116,12 @@ from pandas.io.api import (
     read_table as read_table,
     read_xml as read_xml,
 )
+from pandas.io.api import (
+    read_excel as read_excel,  # pyright: ignore[reportUnknownVariableType]
+)
+from pandas.io.api import (
+    read_orc as read_orc,  # pyright: ignore[reportUnknownVariableType]
+)
 from pandas.io.json._normalize import json_normalize as json_normalize
 from pandas.tseries import offsets as offsets
 from pandas.tseries.api import infer_freq as infer_freq

pandas-stubs/core/frame.pyi

@@ -1083,7 +1083,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def sort_values(
         self,
-        by: _str | Sequence[_str],
+        by: _str | SequenceNotStr[_str],
         *,
         axis: Axis = 0,
         ascending: _bool | Sequence[_bool] = ...,
@@ -1096,7 +1096,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def sort_values(
         self,
-        by: _str | Sequence[_str],
+        by: _str | SequenceNotStr[_str],
         *,
         axis: Axis = 0,
         ascending: _bool | Sequence[_bool] = ...,
@@ -1303,7 +1303,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def groupby(  # type: ignore[overload-overlap] # pyright: ignore reportOverlappingOverload
         self,
-        by: MultiIndex | GroupByObjectNonScalar | None = ...,
+        by: MultiIndex | GroupByObjectNonScalar[Any] | None = ...,
         level: IndexLabel | None = ...,
         as_index: Literal[True] = True,
         sort: _bool = ...,
@@ -1314,7 +1314,7 @@ class DataFrame(NDFrame, OpsMixin, _GetItemHack):
     @overload
     def groupby(  # type: ignore[overload-overlap]
         self,
-        by: MultiIndex | GroupByObjectNonScalar | None = ...,
+        by: MultiIndex | GroupByObjectNonScalar[Any] | None = ...,
         level: IndexLabel | None = ...,
         as_index: Literal[False] = False,
         sort: _bool = ...,

pandas-stubs/io/api.pyi

@@ -2,14 +2,18 @@ from pandas.io.clipboards import read_clipboard as read_clipboard
 from pandas.io.excel import (
     ExcelFile as ExcelFile,
     ExcelWriter as ExcelWriter,
-    read_excel as read_excel,
+)
+from pandas.io.excel import (
+    read_excel as read_excel,  # pyright: ignore[reportUnknownVariableType]
 )
 from pandas.io.feather_format import read_feather as read_feather
 from pandas.io.html import read_html as read_html
 from pandas.io.json import read_json as read_json
-from pandas.io.orc import read_orc as read_orc
+from pandas.io.orc import (
+    read_orc as read_orc,  # pyright: ignore[reportUnknownVariableType]
+)
 from pandas.io.parquet import read_parquet as read_parquet
-from pandas.io.parsers import (
+from pandas.io.parsers.readers import (
     read_csv as read_csv,
     read_fwf as read_fwf,
     read_table as read_table,

pandas-stubs/io/clipboards.pyi

@@ -35,7 +35,7 @@ def read_clipboard(
     header: int | Sequence[int] | Literal["infer"] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | str | Sequence[str | int] | Literal[False] | None = ...,
-    usecols: UsecolsArgType = ...,
+    usecols: UsecolsArgType[Any] = ...,
     dtype: DtypeArg | defaultdict[Any, Any] | None = ...,
     engine: CSVEngine | None = ...,
     converters: dict[int | str, Callable[[str], Any]] = ...,
@@ -94,7 +94,7 @@ def read_clipboard(
     header: int | Sequence[int] | Literal["infer"] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | str | Sequence[str | int] | Literal[False] | None = ...,
-    usecols: UsecolsArgType = ...,
+    usecols: UsecolsArgType[Any] = ...,
     dtype: DtypeArg | defaultdict[Any, Any] | None = ...,
     engine: CSVEngine | None = ...,
     converters: dict[int | str, Callable[[str], Any]] = ...,
@@ -153,7 +153,7 @@ def read_clipboard(
     header: int | Sequence[int] | Literal["infer"] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | str | Sequence[str | int] | Literal[False] | None = ...,
-    usecols: UsecolsArgType = ...,
+    usecols: UsecolsArgType[Any] = ...,
     dtype: DtypeArg | defaultdict[Any, Any] | None = ...,
     engine: CSVEngine | None = ...,
     converters: dict[int | str, Callable[[str], Any]] = ...,

pandas-stubs/io/excel/__init__.pyi

@@ -1,5 +1,7 @@
 from pandas.io.excel._base import (
     ExcelFile as ExcelFile,
     ExcelWriter as ExcelWriter,
-    read_excel as read_excel,
+)
+from pandas.io.excel._base import (
+    read_excel as read_excel,  # pyright: ignore[reportUnknownVariableType]
 )

pandas-stubs/io/excel/_base.pyi

@@ -15,7 +15,6 @@ from typing import (
     overload,
 )
 
-from odf.opendocument import OpenDocument  # pyright: ignore[reportMissingTypeStubs]
 from openpyxl.workbook.workbook import Workbook
 from pandas.core.frame import DataFrame
 import pyxlsb.workbook  # pyright: ignore[reportMissingTypeStubs]
@@ -43,6 +42,10 @@ from pandas._typing import (
     UsecolsArgType,
 )
 
+from odf.opendocument import (  # pyright: ignore[reportMissingTypeStubs] # isort: skip
+    OpenDocument,  # pyright: ignore[reportUnknownVariableType]
+)
+
 @overload
 def read_excel(
     io: (
@@ -59,7 +62,7 @@ def read_excel(
     header: int | Sequence[int] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | Sequence[int] | str | None = ...,
-    usecols: str | UsecolsArgType = ...,
+    usecols: str | UsecolsArgType[Any] = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
     converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
@@ -102,7 +105,7 @@ def read_excel(
     header: int | Sequence[int] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | Sequence[int] | str | None = ...,
-    usecols: str | UsecolsArgType = ...,
+    usecols: str | UsecolsArgType[Any] = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
     converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
@@ -146,7 +149,7 @@ def read_excel(  # type: ignore[overload-cannot-match]
     header: int | Sequence[int] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | Sequence[int] | str | None = ...,
-    usecols: str | UsecolsArgType = ...,
+    usecols: str | UsecolsArgType[Any] = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
     converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
@@ -189,7 +192,7 @@ def read_excel(
     header: int | Sequence[int] | None = ...,
     names: ListLikeHashable | None = ...,
     index_col: int | Sequence[int] | str | None = ...,
-    usecols: str | UsecolsArgType = ...,
+    usecols: str | UsecolsArgType[Any] = ...,
     dtype: str | Dtype | Mapping[str, str | Dtype] | None = ...,
     engine: ExcelReadEngine | None = ...,
     converters: Mapping[int | str, Callable[[Any], Any]] | None = ...,
@@ -312,7 +315,7 @@ class ExcelFile:
         header: int | Sequence[int] | None = ...,
         names: ListLikeHashable | None = ...,
         index_col: int | Sequence[int] | None = ...,
-        usecols: str | UsecolsArgType = ...,
+        usecols: str | UsecolsArgType[Any] = ...,
         converters: dict[int | str, Callable[[Any], Any]] | None = ...,
         true_values: Iterable[Hashable] | None = ...,
         false_values: Iterable[Hashable] | None = ...,
@@ -340,7 +343,7 @@ class ExcelFile:
         header: int | Sequence[int] | None = ...,
         names: ListLikeHashable | None = ...,
         index_col: int | Sequence[int] | None = ...,
-        usecols: str | UsecolsArgType = ...,
+        usecols: str | UsecolsArgType[Any] = ...,
         converters: dict[int | str, Callable[[Any], Any]] | None = ...,
         true_values: Iterable[Hashable] | None = ...,
         false_values: Iterable[Hashable] | None = ...,

pandas-stubs/io/orc.pyi

@@ -1,6 +1,5 @@
 from typing import Any
 
-from fsspec.spec import AbstractFileSystem  # pyright: ignore[reportMissingTypeStubs]
 from pandas import DataFrame
 from pyarrow.fs import FileSystem
 
@@ -12,6 +11,10 @@ from pandas._typing import (
     ReadBuffer,
 )
 
+from fsspec.spec import (  # pyright: ignore[reportMissingTypeStubs] # isort: skip
+    AbstractFileSystem,  # pyright: ignore[reportUnknownVariableType]
+)
+
 def read_orc(
     path: FilePath | ReadBuffer[bytes],
     columns: list[HashableT] | None = None,

pyproject.toml

@@ -303,7 +303,6 @@ reportUnknownArgumentType = false
 reportUnknownLambdaType = false
 reportUnknownMemberType = false
 reportUnknownParameterType = false
-reportUnknownVariableType = false
 reportPrivateUsage = false
 # enable optional checks
 reportMissingModuleSource = true

tests/__init__.py

@@ -135,14 +135,19 @@ def check(
     if dtype is None:
         return actual
 
+    value: Any
     if isinstance(actual, pd.Series):
-        value = actual.iloc[index_to_check_for_type]
+        value = actual.iloc[  # pyright: ignore[reportUnknownVariableType]
+            index_to_check_for_type
+        ]
     elif isinstance(actual, pd.Index):
-        value = actual[index_to_check_for_type]
+        value = actual[  # pyright: ignore[reportUnknownVariableType]
+            index_to_check_for_type
+        ]
     elif isinstance(actual, BaseGroupBy):
-        value = actual.obj  # type: ignore[attr-defined]  # pyright: ignore[reportAttributeAccessIssue]
+        value = actual.obj  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue,reportUnknownVariableType]
     elif hasattr(actual, "__iter__"):
-        value = next(
+        value = next(  # pyright: ignore[reportUnknownVariableType]
             iter(actual)  # pyright: ignore[reportArgumentType,reportCallIssue]
         )
     else:
@@ -151,7 +156,7 @@ def check(
 
     if not isinstance(value, dtype):
         raise RuntimeError(f"Expected type '{dtype}' but got '{type(value)}'")
-    return actual
+    return actual  # pyright: ignore[reportUnknownVariableType]
 
 
 def pytest_warns_bounded(
@@ -161,7 +166,7 @@ def pytest_warns_bounded(
     upper: str | None = None,
     version_str: str | None = None,
     upper_exception: type[Exception] | None = None,
-) -> AbstractContextManager[Any]:
+) -> AbstractContextManager[Any, bool | None]:
     """
     Version conditional pytest.warns context manager
 

tests/arrays/test_extension_array.py

@@ -1,4 +1,5 @@
 # Test common ExtensionArray methods
+
 import numpy as np
 import pandas as pd
 from pandas.core.arrays import ExtensionArray

tests/extension/decimal/array.py

@@ -172,19 +172,19 @@ def __array_ufunc__(
             return NotImplemented
 
         if "out" in kwargs:
-            return arraylike.dispatch_ufunc_with_out(  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue]
+            return arraylike.dispatch_ufunc_with_out(  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue,reportUnknownVariableType]
                 self, ufunc, method, *inputs, **kwargs
             )
 
         inputs = tuple(x._data if isinstance(x, DecimalArray) else x for x in inputs)
         result = getattr(ufunc, method)(*inputs, **kwargs)
 
         if method == "reduce":
-            result = arraylike.dispatch_reduction_ufunc(  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue]
+            result = arraylike.dispatch_reduction_ufunc(  # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue,reportUnknownVariableType]
                 self, ufunc, method, *inputs, **kwargs
             )
             if result is not NotImplemented:
-                return result
+                return result  # pyright: ignore[reportUnknownVariableType]
 
         def reconstruct(
             x: (
@@ -199,16 +199,18 @@ def reconstruct(
             return DecimalArray._from_sequence(x)
 
         if ufunc.nout > 1:
-            return tuple(reconstruct(x) for x in result)
+            return tuple(
+                reconstruct(x)
+                for x in result  # pyright: ignore[reportUnknownVariableType]
+            )
         return reconstruct(result)
 
     def __getitem__(self, item: ScalarIndexer | SequenceIndexer) -> Any:
         if isinstance(item, numbers.Integral):
             return self._data[item]
         # array, slice.
-        item = check_array_indexer(
-            self,
-            item,  # type: ignore[arg-type] # pyright: ignore[reportArgumentType,reportCallIssue]
+        item = check_array_indexer(  # pyright: ignore[reportCallIssue,reportUnknownVariableType]
+            self, item  # type: ignore[arg-type] # pyright: ignore[reportArgumentType]
         )
         return type(self)(self._data[item])
 
@@ -347,10 +349,12 @@ def convert_values(param: Any) -> ExtensionArray | list[Any]:
 
     def value_counts(self, dropna: bool = True) -> Series:
         from pandas.core.algorithms import (  # type: ignore[attr-defined] # isort: skip
-            value_counts,  # pyright: ignore[reportAttributeAccessIssue]
+            value_counts,  # pyright: ignore[reportAttributeAccessIssue,reportAttributeAccessIssue,reportUnknownVariableType]
         )
 
-        return value_counts(self.to_numpy(), dropna=dropna)
+        return value_counts(
+            self.to_numpy(), dropna=dropna
+        )  # pyright: ignore[reportUnknownVariableType]
 
     @classmethod
     def _add_arithmetic_ops(cls) -> None: ...